What does Speechmatics do?

Speechmatics provides speech technology and Voice AI for enterprises, offering accurate Speech-to-Text, Text-to-Speech, and Voice Agent solutions. Our models understand every voice and accent across 55+ languages, helping businesses unlock the full potential of voice data.

How accurate is Speechmatics Speech-to-Text?

Speechmatics delivers best-in-market accuracy, achieving up to 99% word accuracy and 96% medical keyword recall in industry benchmarks. Our models handle multiple accents, noisy environments, and multi speakers with ease.

What makes Speechmatics Text-to-Speech different?

Our low-latency Text-to-Speech (TTS) delivers lifelike, human-sounding voices with sub-150ms latency that is ideal for real-time conversations. Developers can stream natural speech in multiple voices and deploy it in the cloud, hybrid, or on-prem for privacy and control.

Can I build real-time voice agents with Speechmatics?

Our voice AI enables developers to build real-time voice agents that listen, understand, and respond naturally. Plug in fast with a flexible API and native integrations to power your AI voice agents.

Which industries use Speechmatics?

Speechmatics is trusted by organizations in media, healthcare, contact center, medical, finance, legal, education, and accessibility. Our technology powers transcription, translation, call analytics, and voice AI applications worldwide.

What’s in an acronym?

Acronyms are often understood and used more than their unabbreviated form. This occurs nearly everywhere, for example, 'BLT' is just as understood in a restaurant as 'Bacon Lettuce and Tomato.'

In some cases, the acronym is more common than the complete form, PM is used for afternoon and hardly ever do people say “Post Meridian”, and MP4 is used for the file format and I don’t think I have ever heard anyone say 'Moving Picture Experts Group Advanced Video Coding' format (MPEG-4 AVC)...

Why is it tricky to get right?

Although there are cases where the pronunciation of the acronym is the same as the written form (NASA for example), it is often not the case, and so phonetic transcriptions do not work. You may also just expect these to work, but many of them are industry or use case specific so without tailoring to specific markets it is impossible to solve all cases.

Can Speech Recognition fix that too?

The Custom Dictionary feature in Speechmatics ASR products can help solve these kinds of issues like a human would. This involves providing just a little context to help the ASR along. Just adding the required form to the Custom Dictionary can help detect the acronym but that will not work some of the time, and for cases such as 'MP4' or 'ASR' it cannot. But all is not lost Speechmatics can help you here too.

Watch this space for our newest feature addition, coming soon…

Watch the example below!

Ian Firth, Speechmatics